如何从picamera（python，opencv）中提取数组中的图像

Question

我在皮卡梅拉很新。 现在，我想通过摄像头检测简单的动作，并使用cv2.absdiff() 。 但是，我得到的数组（image1，image2）是相同的。 如何获得用于抽象的不同数组或获取数组中的元素（图像）？ 这是我的代码：

import sys
sys.path.append('/usr/local/lib/python2.7/site-packages')
from picamera.array import PiRGBArray
from picamara import PiCamera
import cv2
import time
import time
import numpy as np

camera = PiCamera()
camera.resolution = (640,480)
camera.framerate = 32
rawCapture = PiRGBArray(camera,size=(640,480))

time.sleep(0.1)

for frame in camera.capture_continuous(rawCapture,format="bgr",use_video_port=True):

    image1 = frame.array
    gray1 = cv2.cvtColor(image1,cv2.COLOR_BGR2GRAY)
    cv2.waitKey(33)
    image2 = frame.array
    gray2 = cv2.cvtColor(image2,cv2.COLOR_BGR2GRAY)

    diff = cv2.absdiff(gray1,gray2)
    cv2.imshow("DIFF",diff)

    key = cv2.waitKey(33)&0xFF
    rawCapture.truncate(0)
    if key == ord("q"):
        break

Answer 1

您的脚本正在尝试将同一帧与其自身进行比较，这显然不会显示任何差异。

一种方法是在开始循环之前获取一个初始帧，然后将其与任何后续帧进行比较，如下所示：

import sys
#sys.path.append('/usr/local/lib/python2.7/site-packages')
from picamera.array import PiRGBArray
from picamara import PiCamera
import cv2
import time
import time
import numpy as np

camera = PiCamera()
camera.resolution = (640,480)
camera.framerate = 32
rawCapture = PiRGBArray(camera,size=(640,480))
time.sleep(0.1)
initial_frame = camera.capture(rawCapture, format="bgr", use_video_port=True):

for frame in camera.capture_continuous(rawCapture, format="bgr", use_video_port=True):
    cv2.waitKey(33)
    image2 = frame.array
    gray = cv2.cvtColor(image2, cv2.COLOR_BGR2GRAY)

    diff = cv2.absdiff(initial_frame, gray)
    cv2.imshow("DIFF", diff)

    key = cv2.waitKey(33) & 0xFF
    rawCapture.truncate(0)

    if key == ord("q"):
        break 

您可以进一步增强它以定期更新初始帧，以解决对背景的任何长期更改。